Zosma QA

Zosma QA is an open-source testing-focused agent harness and orchestration framework created by Zosma AI. It provides scaffolding, structured prompt templates, and execution environments designed to coordinate coding agents for automated software testing and quality engineering tasks. In practical workflows, Zosma QA acts as the bridge between AI coding agents (including OpenCode and Pi coding agent environments) and established test frameworks. It coordinates test generation, execution, and debugging across web browsers, mobile platforms, and backend services by utilizing pre-configured prompt architectures and directory-aware spec runners. Unlike general-purpose CLI coding agents that focus on generic software authoring, Zosma QA specializes strictly in the QA lifecycle. It embeds domain-specific tooling and conventions for Playwright (web E2E), Appium (mobile automation), Python testing frameworks, and k6 (load and performance testing), including sanitization utilities for UI element selectors and structured spec directory management. Zosma QA is distributed under open-source terms and publishes modular packages through npm (such as `@zosmaai/zosma-qa-k6`) alongside its core GitHub monorepo.

Tags: AI, ai agent, cli, coding agent, developer tools, OpenSource

Visit Zosma QA

Key features

• Playwright Test Orchestration — Scaffolds, generates, and maintains browser E2E test specs with structured agent prompt workflows. - Appium Mobile Automation — Generates and verifies mobile test scripts with built-in locator and XPath selector sanitization. - k6 Load Testing — Provides dedicated modules (@zosmaai/zosma-qa-k6) for authoring and running performance and load tests. - Coding Agent Configuration Profiles — Supplies native prompt setups and harness configurations for coding agents like OpenCode and Pi. - Multi-Language Support — Ships templates and scaffolds for JavaScript/TypeScript and Python test runners. - CLI Project Scaffolding — Interactive project initialization scripts that bootstrap QA test suites directly into target repositories.

Use cases

Use Case: Automated Playwright E2E Suite Generation A QA engineer needs to generate end-to-end browser tests for user flows. Using Zosma QA's Playwright integration and agent prompts, the agent writes consistent test specs in the designated specs directory and verifies execution against the target web application.

Use Case: Mobile Test Automation with Appium A mobile development team needs automated UI regression tests for iOS and Android apps. Zosma QA guides coding agents to produce Appium tests with escaped selector strings and robust selector handling, minimizing locator flakiness.

Use Case: Load and Performance Testing Scenarios A backend engineer wants to simulate endpoint load before a deployment. Zosma QA leverages the @zosmaai/zosma-qa-k6 tooling to configure AI agents to draft, parameterize, and run k6 load testing scripts.

Who it is for

Zosma QA is built for QA automation engineers, SDETs, and software developers focused on structuring and executing test automation suites with AI agents. It is not intended as a general-purpose coding assistant for unrelated feature engineering or infrastructure provisioning.

Install guide

Installation Install the package via npm (or clone the repository for local harness development): bash # Standard npm installation npm install @zosmaai/zosma-qa # Or clone the monorepo directly git clone https://github.com/zosmaai/zosma-qa.git cd zosma-qa npm install To install the k6 performance module: bash npm install @zosmaai/zosma-qa-k6

First Run Initialize your test project and verify that the agent prompt configurations (e.g., .opencode or .pi directories) are placed in your repository root: bash # Initialize test harness configuration npx zosma-qa init Ensure your target framework dependencies (Playwright, Appium, or k6) and required LLM API keys are configured in your environment.

Example Session Run the agent harness to scaffold and validate a Playwright test spec: bash # Generate and execute test specs using the configured agent prompts npx zosma-qa generate --framework playwright --target "./specs/login-flow.spec.ts"

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

• AgentSight — AgentSight is an open-source, local-first observability and profiling harness for AI coding agents developed by the Eunomia project. Operating similarly…
• Headroom — Headroom is an open-source agent orchestration harness and proxy runtime developed by Headroom Labs. Engineered in Rust with multi-language bindings,…
• OpenCode — OpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.…
• SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
• OpenHands — OpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environment…
• Plandex — Plandex is an open-source terminal-based AI coding agent designed to handle complex, multi-file engineering tasks in large codebases. Created by…